activity
20172020
most citedTowards Good Practices for Deep 3D Hand Pose Estimation

48 citations · 51 across the 3 of their papers we have counts for

collaborators

6 papers

cs.CV2020

Adaptive Pixel-wise Structured Sparse Network for Efficient CNNs

Chen Tang, Wenyu Sun, Zhuqing Yuan +1

To accelerate deep CNN models, this paper proposes a novel spatially adaptive framework that can dynamically generate pixel-wise sparsity according to the input image. The sparse s…

cs.CV20203 cited

ADMP: An Adversarial Double Masks Based Pruning Framework For Unsupervised Cross-Domain Compression

Xiaoyu Feng, Zhuqing Yuan, Guijin Wang +1

Despite the recent progress of network pruning, directly applying it to the Internet of Things (IoT) applications still faces two challenges, i.e. the distribution divergence betwe…

cs.CV2019

Bi-stream Pose Guided Region Ensemble Network for Fingertip Localization from Stereo Images

Guijin Wang, Cairong Zhang, Xinghao Chen +3

In human-computer interaction, it is important to accurately estimate the hand pose especially fingertips. However, traditional approaches for fingertip localization mainly rely on…

cs.CV2018

Two-Stream Binocular Network: Accurate Near Field Finger Detection Based On Binocular Images

Yi Wei, Guijin Wang, Cairong Zhang +3

Fingertip detection plays an important role in human computer interaction. Previous works transform binocular images into depth images. Then depth-based hand pose estimation method…

cs.CV2018

Interactive Hand Pose Estimation: Boosting accuracy in localizing extended finger joints

Cairong Zhang, Guijin Wang, Hengkai Guo +3

Accurate 3D hand pose estimation plays an important role in Human Machine Interaction (HMI). In the reality of HMI, joints in fingers stretching out, especially corresponding finge…

cs.CV201748 cited

Towards Good Practices for Deep 3D Hand Pose Estimation

Hengkai Guo, Guijin Wang, Xinghao Chen +1

3D hand pose estimation from single depth image is an important and challenging problem for human-computer interaction. Recently deep convolutional networks (ConvNet) with sophisti…